Execution-harness refinement
Lets LLM agents automatically evolve their prompts, tools, and memory for open-world tasks without ground-truth verifiers.
Loading page…
Coding / product dossier
Harness²
A recursive framework that lets LLM agents refine their prompts, tools, and memory without verifiers.
Product brief
What Harness² does.
Harness² from Google Research is a plug-and-play recursive agent harnessing framework that lets LLM agents automatically evolve their execution harnesses (prompts, tools, memory) for open-world tasks—without ground-truth verifiers. Dual recursion: task-level Propose-Probe-Compose refinement + harnessing-level accumulation of reusable experience. Up to +11.5 points on professional benchmarks like WorkBuddy-Bench.